ImmersedPrivacy - Social Context Rating Error (Audio as Text): leaderboard

Metric: Mean absolute error (Tier 2: the model's 1-5 appropriateness rating of each candidate action against the mean human rating; audio replaced by a text description of the soundscape (Tier 2) or the dialogue transcript (Tier 3); lower is better). Source: arxiv.org. Saturation forecast: Around July 2027. 12 models tracked.

Top models

#ModelScore
1GPT-5.4 (2026-03-05)1.03
2Gemini 3 Flash (Preview) (Low)1.24
3Gemini 3 Flash (Preview) (High)1.25
4Qwen 3.5 27B (Thinking)1.26
5GPT-4o Mini (2024-07-18)1.32
6Gemini 3.1 Pro (Preview) (Low)1.37
7Qwen 3.5 27B (Non-reasoning)1.39
8Gemini 3.1 Pro (Preview) (High)1.44

Interactive version: theaggregate.ai/benchmark?slug=immersedprivacy-social-context-rating-error-audio-as-text · How It Works · Data refreshed daily, snapshot 2026-09-26.